{"id":"W2288957490","doi":"10.20355/c5kg6p","title":"Fairness of Standardized Assessments: Discrepancy between Provincial and Territorial Results","year":2016,"lang":"en","type":"article","venue":"Journal of Contemporary Issues in Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Psychology; Section (typography); Standardized test; Regional science; Political science; Sociology; Mathematics education; Business; Advertising","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1232895,0.0004484154,0.0009433019,0.003748409,0.004782761,0.00757642,0.00259915,0.0008480359,0.002335225],"category_scores_gemma":[0.3083293,0.0003881706,0.0006289971,0.006365652,0.004325667,0.002690236,0.004163487,0.001938531,0.000420663],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.02039687,"about_ca_system_score_gemma":0.03485588,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.3229007,"about_ca_topic_score_gemma":0.3812532,"domain_scores_codex":[0.8152125,0.07542115,0.01642333,0.008219205,0.07790162,0.006822335],"domain_scores_gemma":[0.6927815,0.09790853,0.02641622,0.02510105,0.1529975,0.004795142],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001111395,0.0002110757,0.3658223,0.0009786687,0.0006297818,0.0006215069,0.0655159,0.007815163,0.003816616,0.1151078,0.02134939,0.4170204],"study_design_scores_gemma":[0.0001470568,0.0006796202,0.704958,0.002358752,0.0004371322,0.0006870932,0.07074696,0.02471144,0.01577314,0.09233153,0.08655247,0.0006168257],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7136894,0.002600313,0.1180698,0.02436952,0.00103258,0.001338076,0.001865166,0.0006176156,0.1364174],"genre_scores_gemma":[0.9863906,0.0001650194,0.01005545,0.0004723913,0.00003437845,0.0001235468,0.0001864752,0.0000519818,0.002520167],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6770993,"threshold_uncertainty_score":0.6520252,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1183209692239725,"score_gpt":0.5121441527236013,"score_spread":0.3938231834996287,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}